7 Variational Autoencoders

7.1 Training

Variational encoders are separately trained for each bird.

Figure 7.1: The Calinski-Harabasz Index (ratio of between-cluster to within-cluster variance) plateaus before the reconstruction loss for bird 7358.

Variational autoencoders
Input (left) and decoded (right) syllables.

Figure 7.2: Input (left) and decoded (right) syllables.

Traversing the embedding space from the centroid of syllable "i" to each other syllable centroid.

Figure 7.3: Traversing the embedding space from the centroid of syllable ā€œiā€ to each other syllable centroid.

7.2 Syllable Clustering

Bird 7358 (66-68 DPH) has relatively stable syllables and song syntax, while bird 6951 (59-63 DPH) has more variable syllables and syntax 8.1.

Syllable clusters from embedded dimensions.Syllable clusters from embedded dimensions.

Figure 7.4: Syllable clusters from embedded dimensions.

Figure 7.5: UMAP projection of song trajectory with neuron spikes shown as dots.

Figure 7.5: UMAP projection of song trajectory with neuron spikes shown as dots.

Figure 7.5: UMAP projection of song trajectory with neuron spikes shown as dots.

Figure 7.5: UMAP projection of song trajectory with neuron spikes shown as dots.

Figure 7.5: UMAP projection of song trajectory with neuron spikes shown as dots.